Did someone try or use VoxCPM? Here is the link: https://github.com/OpenBMB/VoxCPM

I spent more times to learn and use papecat framework. I thought, I can deliver cheap service solutions for local business. Then, I spent more time and acost in development and deployment. When I compared the price is similar or little bit less than vapi or retail. Namely, this path more expensive because I will responsible about maintenance, reliable, and also solutions. Then, I found for local business, it chosen this ready deployment platform such as vapi or else is more sufficient direction. Did you find a way to reduce the cost of development, deployment, and maintenance?

Want a REAL production-ready n8n deployment? In this video we break down the n8n-aiwithapex infrastructure stack and why it’s a massive upgrade over a “basic docker-compose n8n” setup. You’ll see how this project implements a full queue-mode architecture with: - n8n-main (Editor/API) separated from execution - Redis as the queue broker - Multiple n8n workers for horizontal scaling - External task runners (isolated JS/Python execution) for safer Code node workloads - PostgreSQL persistence with tuning + initialization - ngrok for quick secure access in WSL2/local dev We’ll also cover the “Ops” side that most tutorials ignore: - Comprehensive backups (Postgres + Redis + n8n exports + env backups) - Offsite sync + optional GPG encryption - Health checks, monitoring, queue depth, and log management scripts - Restore + disaster recovery testing so you can recover fast - Dual deployment paths: WSL2 for local + Coolify for cloud/production If you’re building automations for clients, running n8n for a team, or scaling AI workflows, this architecture is the blueprint: separation of concerns, isolation, scaling, and recoverability. Youtube video: https://youtu.be/HzgrId0kgfw?si=0bzdvDgJW4dLApfi Repo: https://github.com/moshehbenavraham/n8n-aiwithapex

I have created a Voice AI Agent that's able to; • Calls leads in less than 60 seconds as soon as they fill the ad form. • Qualifies the lead. • Books appointments on the business calendar • Updates the CRM The Voice AI Agent qualifies the lead in real-time, filters out spammy numbers and fake leads, books appointments on your calendar, and sends you the legit leads. It then analyzes the call, categorizes the lead and instantly updates your CRM. 𝐓𝐞𝐜𝐡 𝐬𝐭𝐚𝐜𝐤 • I used Livekit & Twilio. Used Amazon Nova Sonic Realtime API • Deployed the agent to livekit cloud using github actions.

Hey everyone, Thank you so much for your patience while we got this community ready to launch. It’s finally happening! 🎉 I’ve put together a short video explaining why I started this group and what it’s all about. I’m really excited to meet all of you — passionate, like-minded people working in the voice AI space. Our first meetup is next Friday, and it’ll be all about getting to know each other, hearing about your voice AI projects, and understanding what you’d like to learn on here. In the meantime, let’s start with introductions right here under this post 👇 Please share: - Who you are - What you’re building or working on - What you’d love to learn or explore within this community Can’t wait to see what everyone’s up to!